{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T20:37:44Z","timestamp":1761597464343,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,5]]},"DOI":"10.1109\/icassp.2013.6637646","type":"proceedings-article","created":{"date-parts":[[2013,10,29]],"date-time":"2013-10-29T23:19:46Z","timestamp":1383088786000},"page":"246-250","source":"Crossref","is-referenced-by-count":13,"title":["Dual-layer bag-of-frames model for music genre classification"],"prefix":"10.1109","author":[{"given":"Chin-Chia Michael","family":"Yeh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Hsuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2161264"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553463"},{"journal-title":"LIBSVM A library for support vector machines","year":"2001","author":"chang","key":"35"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2009.2030345"},{"key":"36","article-title":"LIBLINEAR: A library for large linear classification","author":"fan","year":"2008","journal-title":"J Machine Learning Research"},{"key":"15","first-page":"663","article-title":"Multiscale temporal fusion by boosting for music classification","author":"foucard","year":"2011","journal-title":"ISMIR"},{"key":"33","doi-asserted-by":"publisher","DOI":"10.1145\/2390848.2390851"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1561\/2200000015"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.62"},{"key":"13","article-title":"Audio-based music classification with a pretrained convolutional network","author":"dieleman","year":"2011","journal-title":"ISMIR"},{"key":"14","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-652","article-title":"Pooling robust shift-invariant sparse representations of acoustic signals","author":"huang","year":"2012","journal-title":"InterSpeech"},{"key":"37","article-title":"A survey of evaluation in music genre recognition","author":"sturm","year":"2012","journal-title":"Adaptive Multimedia Retrieval"},{"key":"11","first-page":"1096","article-title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","author":"lee","year":"2009","journal-title":"NIPS"},{"key":"38","article-title":"A large-scale evaluation of acoustic and subjective music similarity measures","author":"berenzweig","year":"2003","journal-title":"Computer Music Journal"},{"key":"12","first-page":"339","article-title":"Learning features from music audio with deep belief networks","author":"hamel","year":"2010","journal-title":"ISMIR"},{"key":"21","first-page":"81","article-title":"Sparse atomic modeling of audio: A review","author":"depalle","year":"2011","journal-title":"Proc Int Conf Digital Audio Effects"},{"key":"20","first-page":"681","article-title":"Unsupervised learning of sparse features for scalable audio classification","author":"henaff","year":"2011","journal-title":"ISMIR"},{"key":"22","first-page":"608","article-title":"Multipitch estimation of piano music by exemplar-based sparse representation","volume":"14","author":"lee","year":"2012","journal-title":"IEEE TMM"},{"key":"23","first-page":"565","article-title":"Learning sparse feature representations for music annotation and retrieval","author":"nam","year":"2012","journal-title":"ISMIR"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2013.6607505"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1038\/nature04485"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827596304010"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.1214\/009053604000000067"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"3","article-title":"Learning the similarity of audio music in bag-of-frames representation from tagged music data","author":"wang","year":"2011","journal-title":"ISMIR"},{"key":"2","first-page":"399","article-title":"Learning tags that vary within a song","author":"mandel","year":"2010","journal-title":"ISMIR"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1661198"},{"key":"10","first-page":"403","article-title":"Deep architectures and automatic feature learning in music informatics","author":"humphrey","year":"2012","journal-title":"ISMIR"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-9019-7"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1145\/2324796.2324859"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396323"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2000.869637"},{"key":"5","first-page":"139","article-title":"Unsupervised learning of local features for music classification","author":"wu?lfing","year":"2012","journal-title":"ISMIR"},{"key":"31","article-title":"MIR in Matlab (II): A toolbox for musical feature extraction from audio","author":"lartillot","year":"2007","journal-title":"ISMIR"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2199109"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2112333"},{"key":"8","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1109\/MSP.2010.939537","article-title":"Dictionary learning: What is the right representation for my signal?","volume":"28","author":"tosic","year":"2011","journal-title":"IEEE Signal Processing Magazine"}],"event":{"name":"ICASSP 2013 - 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2013,5,26]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2013,5,31]]}},"container-title":["2013 IEEE International Conference on Acoustics, Speech and Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6619549\/6637585\/06637646.pdf?arnumber=6637646","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T22:39:54Z","timestamp":1646951994000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6637646\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp.2013.6637646","relation":{},"subject":[],"published":{"date-parts":[[2013,5]]}}}